{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BVQMEQTSGZQ5HG45I7FUTURXMO","short_pith_number":"pith:BVQMEQTS","schema_version":"1.0","canonical_sha256":"0d60c242723661d39b9d47cb49d23763a892afea0a5162a120e4c6224626b2f2","source":{"kind":"arxiv","id":"2506.10716","version":1},"attestation_state":"computed","paper":{"title":"PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haohan Wang, Yaoning Yu, Ye Yu","submitted_at":"2025-06-12T14:05:09Z","abstract_excerpt":"Large reasoning models (LRMs) such as Claude 3.7 Sonnet and OpenAI o1 achieve strong performance on mathematical benchmarks using lengthy chain-of-thought (CoT) reasoning, but the resulting traces are often unnecessarily verbose. This inflates token usage and cost, limiting deployment in latency-sensitive or API-constrained settings. We introduce PREMISE (PRompt-based Efficient Mathematical Inference with Strategic Evaluation), a prompt-only framework that reduces reasoning overhead without modifying model weights. PREMISE combines trace-level diagnostics with gradient-inspired prompt optimiza"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.10716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T14:05:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a481055435e4f76865a5f2f4714cf9bd4514c9d7f6d8bc8b431b9d45c134765e","abstract_canon_sha256":"ecb3b006e302b4b2510466aa847012d67b22f37921d57d14c627d872e23220ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:29.080666Z","signature_b64":"zaboMUig3RCWH9nqY/Sd+YzdiEaTki45l3bfO+jrenrLFtEev0eElRA2GRukFNbamNfJwi+V5vLDqtUvASvBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d60c242723661d39b9d47cb49d23763a892afea0a5162a120e4c6224626b2f2","last_reissued_at":"2026-07-05T11:20:29.080041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:29.080041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Haohan Wang, Yaoning Yu, Ye Yu","submitted_at":"2025-06-12T14:05:09Z","abstract_excerpt":"Large reasoning models (LRMs) such as Claude 3.7 Sonnet and OpenAI o1 achieve strong performance on mathematical benchmarks using lengthy chain-of-thought (CoT) reasoning, but the resulting traces are often unnecessarily verbose. This inflates token usage and cost, limiting deployment in latency-sensitive or API-constrained settings. We introduce PREMISE (PRompt-based Efficient Mathematical Inference with Strategic Evaluation), a prompt-only framework that reduces reasoning overhead without modifying model weights. PREMISE combines trace-level diagnostics with gradient-inspired prompt optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10716","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.10716/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.10716","created_at":"2026-07-05T11:20:29.080175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10716v1","created_at":"2026-07-05T11:20:29.080175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10716","created_at":"2026-07-05T11:20:29.080175+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVQMEQTSGZQ5","created_at":"2026-07-05T11:20:29.080175+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVQMEQTSGZQ5HG45","created_at":"2026-07-05T11:20:29.080175+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVQMEQTS","created_at":"2026-07-05T11:20:29.080175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO","json":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO.json","graph_json":"https://pith.science/api/pith-number/BVQMEQTSGZQ5HG45I7FUTURXMO/graph.json","events_json":"https://pith.science/api/pith-number/BVQMEQTSGZQ5HG45I7FUTURXMO/events.json","paper":"https://pith.science/paper/BVQMEQTS"},"agent_actions":{"view_html":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO","download_json":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO.json","view_paper":"https://pith.science/paper/BVQMEQTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10716&json=true","fetch_graph":"https://pith.science/api/pith-number/BVQMEQTSGZQ5HG45I7FUTURXMO/graph.json","fetch_events":"https://pith.science/api/pith-number/BVQMEQTSGZQ5HG45I7FUTURXMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO/action/storage_attestation","attest_author":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO/action/author_attestation","sign_citation":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO/action/citation_signature","submit_replication":"https://pith.science/pith/BVQMEQTSGZQ5HG45I7FUTURXMO/action/replication_record"}},"created_at":"2026-07-05T11:20:29.080175+00:00","updated_at":"2026-07-05T11:20:29.080175+00:00"}